=Coffee episode artwork

EPISODE · Feb 16, 2026 · 55 MIN

=Coffee

from Hacked · host Hacked

A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict. Learn more about your ad choices. Visit podcastchoices.com/adchoices

A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been researching how to trick these models. Their solution, a technique called "Echogram" involves words with such positive statistical sentiment — such overwhelming good vibes — that it flips that verdict. Learn more about your ad choices. Visit podcastchoices.com/adchoices

NOW PLAYING

=Coffee

0:00 55:45

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Frequently Asked Questions

How long is this episode of Hacked?

This episode is 55 minutes long.

When was this Hacked episode published?

This episode was published on February 16, 2026.

What is this episode about?

A lot of modern AI models have a kind of security guard layer that sits in front of them. Its job? A binary choice as to whether the prompt heading into the model is safe or not. Kasimir Schulz, a lead security researcher at HiddenLayer, has been...

Can I download this Hacked episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!